INDEX

Explanations

references to specific locations and places

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

 lifetime

-0.16

 cavity

-0.16

ounter

-0.15

-anchor

-0.15

-0.14

urgeon

-0.14

ieu

-0.14

 Liver

-0.14

 Mine

-0.14

 flesh

-0.14

POSITIVE LOGITS

 Harding

0.20

VICE

0.17

UREMENT

0.16

æ±ł

0.15

","\

0.15

ç£¨

0.15

Porno

0.14

à¥Ĥà¤®

0.14

.Pool

0.14

 Powers

0.13

Activations Density 0.040%

references to specific locations and places

No Comments

No Known Activations