INDEX

Explanations

terms related to injuries and disabilities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

odyn

-0.16

rai

-0.14

ertz

-0.14

Ø¯ÙĨ

-0.14

âĻª↵↵

-0.14

istence

-0.14

 Knee

-0.14

izedName

-0.13

 Hearth

-0.13

 Herz

-0.13

POSITIVE LOGITS

 Claude

0.16

Pont

0.16

 pont

0.14

jis

0.14

ÑĢÐ°Ð²Ð°

0.14

*>*

0.14

ota

0.13

 Philipp

0.13

OWER

0.13

 recurs

0.13

Activations Density 0.042%

terms related to injuries and disabilities

No Comments

No Known Activations