INDEX

Explanations

references to political objections or actions in legislative contexts

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

ycastle

-0.15

dlg

-0.15

rego

-0.14

ActionCreators

-0.14

-election

-0.14

 ãĥį

-0.13

Î¸Î·

-0.13

 Merkel

-0.13

ilet

-0.13

election

-0.13

POSITIVE LOGITS

áº¯ng

0.17

oppins

0.16

0.15

.motion

0.15

 motion

0.15

ç

0.15

Coc

0.14

awy

0.14

 Members

0.14

Motion

0.13

Activations Density 0.513%

references to political objections or actions in legislative contexts

No Comments

No Known Activations