INDEX

Explanations

phrases indicating a political context or position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Fare

-0.16

fare

-0.16

 Expansion

-0.15

aro

-0.15

aru

-0.14

isay

-0.14

 expansion

-0.14

olas

-0.13

Ã©l

-0.13

Mas

-0.13

POSITIVE LOGITS

kola

0.16

argar

0.15

azÄ±

0.14

ë²Ķ

0.14

 bergen

0.14

azzi

0.14

opsis

0.14

iben

0.14

gard

0.14

adesh

0.13

Activations Density 0.003%

phrases indicating a political context or position

No Comments

No Known Activations