INDEX

Explanations

instances of the word "meet" and its variations, indicating a focus on encounters and social interactions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enheim

-0.15

uj

-0.15

cano

-0.14

å¸Ń

-0.14

pic

-0.14

Î¹Î±Î½

-0.14

 Downing

-0.14

TOT

-0.14

idth

-0.14

enties

-0.14

POSITIVE LOGITS

ropolis

0.28

ropolitan

0.22

ioned

0.22

tle

0.22

_requirements

0.18

 deadlines

0.17

 resistance

0.16

onym

0.16

atars

0.16

amodel

0.15

Activations Density 0.026%

instances of the word "meet" and its variations, indicating a focus on encounters and social interactions

No Comments

No Known Activations

instances of the word "meet" and its variations, indicating a focus on encounters and social interactions

No Comments

No Known Activations