INDEX

Explanations

references to political events, specifically inaugurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iena

-0.15

wrap

-0.14

apan

-0.14

ä¼

-0.14

WithData

-0.14

/he

-0.14

Ø¨ÙĬØ¹

-0.14

Ø¬Ø§Øª

-0.13

aÅ¼

-0.13

POSITIVE LOGITS

allest

0.16

Gri

0.14

lide

0.14

 Goodman

0.14

paired

0.13

/locale

0.13

Mus

0.13

LOB

0.13

Cleanup

0.13

Reuse

0.13

Activations Density 0.017%

references to political events, specifically inaugurations

No Comments

No Known Activations

references to political events, specifically inaugurations

No Comments

No Known Activations