INDEX

Explanations

references to candidates in political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ington

-0.16

oya

-0.16

baÅŁ

-0.16

undi

-0.15

rahim

-0.15

azor

-0.15

æł·çļĦ

-0.15

canf

-0.15

thing

-0.15

coming

-0.15

POSITIVE LOGITS

who

0.23

 whom

0.22

who

0.21

hip

0.18

hood

0.17

êµ°

0.17

ion

0.17

ä»¬

0.16

/app

0.16

 pool

0.16

Activations Density 0.050%

references to candidates in political contexts

No Comments

No Known Activations