INDEX

Explanations

terms related to political affiliations and endorsements

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

thora

-0.15

ouser

-0.15

áº¯m

-0.15

oire

-0.14

ocity

-0.14

agus

-0.14

edir

-0.13

 NÄĽm

-0.13

 Tradable

-0.13

åŀ

-0.13

POSITIVE LOGITS

Don

1.25

Don

1.16

don

1.13

don

1.11

DON

1.09

DON

1.03

_don

0.98

 ÐĶÐ¾Ð½

0.96

 donor

0.94

 donors

0.84

Activations Density 0.287%

terms related to political affiliations and endorsements

No Comments

No Known Activations