INDEX

Explanations

disclaimers related to legal and medical advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çŁ¢

-0.15

oren

-0.15

lg

-0.15

å½

-0.14

 Lois

-0.14

ato

-0.14

Cot

-0.13

 billing

-0.13

 Visibility

-0.13

POSITIVE LOGITS

 reader

0.20

 neither

0.20

 reliance

0.19

 viewer

0.18

 readers

0.18

Viewer

0.17

 viewers

0.17

 Viewer

0.17

Neither

0.17

 Reader

0.16

Activations Density 0.054%

disclaimers related to legal and medical advice

No Comments

No Known Activations