INDEX

Explanations

dialogue and expressions of communication difficulties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ixon

-0.16

orth

-0.15

 Coordinate

-0.15

 Strand

-0.14

onta

-0.14

äºĨè§£

-0.14

orra

-0.14

ont

-0.14

apa

-0.13

Coordinate

-0.13

POSITIVE LOGITS

LEAR

0.15

mtx

0.15

ÑĢÐ°Ñģ

0.15

å®ľ

0.14

Ã½t

0.14

 Licence

0.14

oteca

0.14

_spin

0.14

INET

0.14

paque

0.14

Activations Density 0.252%

dialogue and expressions of communication difficulties

No Comments

No Known Activations