INDEX

Explanations

references to individuals and their relationships in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ebek

-0.19

lub

-0.17

ruba

-0.16

ikip

-0.15

aldi

-0.15

juana

-0.15

gte

-0.15

oldem

-0.15

ignal

-0.15

igham

-0.15

POSITIVE LOGITS

Ã¡Å¾

0.15

 lessons

0.15

gag

0.14

 throughout

0.14

ither

0.14

Cov

0.14

 STACK

0.14

 Throughout

0.14

olini

0.14

Activations Density 0.314%

references to individuals and their relationships in various contexts

No Comments

No Known Activations