INDEX

Explanations

references to political and social justice issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

.asp

-0.14

RowAt

-0.14

ard

-0.13

avage

-0.13

ystone

-0.13

 Trouble

-0.13

sect

-0.13

iza

-0.12

ROUGH

-0.12

cribing

-0.12

POSITIVE LOGITS

onda

0.16

ederland

0.15

ahoma

0.15

auce

0.14

uni

0.14

hazi

0.14

angi

0.14

isas

0.14

yang

0.14

Protected

0.14

Activations Density 0.022%

references to political and social justice issues

No Comments

No Known Activations