INDEX

Explanations

references to political or government-related entities and their influence on society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

anza

-0.14

ioni

-0.14

oupon

-0.14

tar

-0.14

itas

-0.13

Mae

-0.13

Mov

-0.13

elsinki

-0.13

obao

-0.13

POSITIVE LOGITS

 alike

0.28

 respectively

0.17

 Holt

0.17

odzi

0.15

ROL

0.15

ascar

0.15

 ÑĤÐ¾Ð¶Ðµ

0.15

çĢ¬

0.14

/root

0.14

ë¢°

0.14

Activations Density 0.240%

references to political or government-related entities and their influence on society

No Comments

No Known Activations