INDEX

Explanations

mentions of political parties and related terms

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

nect

-0.18

emos

-0.18

most

-0.16

ister

-0.16

ly

-0.15

lea

-0.15

ÛĮØ±

-0.15

era

-0.15

Ø§ØªÛĮ

-0.15

POSITIVE LOGITS

ing

0.21

opleft

0.18

ÄĽÅ¾

0.16

ldr

0.15

unately

0.15

ctrine

0.15

AGMA

0.15

oret

0.15

ING

0.15

arians

0.15

Activations Density 0.030%

mentions of political parties and related terms

No Comments

No Known Activations