INDEX

Explanations

specific nouns or terms that indicate a location or identifier

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 çĤ

-0.18

 meslek

-0.17

ÑĢÑĥÐ½

-0.16

-0.15

olini

-0.15

anj

-0.15

olah

-0.14

ibu

-0.14

 nomine

-0.14

rup

-0.14

POSITIVE LOGITS

aign

0.17

alker

0.16

 pick

0.15

in

0.15

 surrounded

0.15

ex

0.15

 straight

0.15

 besides

0.15

Toolkit

0.14

Activations Density 0.011%

specific nouns or terms that indicate a location or identifier

No Comments

No Known Activations