INDEX

Explanations

references to government entities and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

otel

-0.16

ALA

-0.15

dG

-0.14

Ã§ak

-0.14

eti

-0.14

fid

-0.14

alse

-0.14

 daylight

-0.14

Ã²ng

-0.14

POSITIVE LOGITS

 Interr

0.15

 likewise

0.15

ãĥĸãĥŃ

0.15

-upper

0.15

GetInt

0.14

Ð²Ð°Ð½Ð¾

0.14

abis

0.14

ItemSelected

0.13

idad

0.13

 Ranger

0.13

Activations Density 0.009%

references to government entities and their actions

No Comments

No Known Activations