INDEX

Explanations

references to conditional actions or requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

efa

-0.16

Bai

-0.16

EFA

-0.14

istol

-0.14

ØµØª

-0.14

emble

-0.14

Ø¤ÙĪÙĦ

-0.14

ispecies

-0.13

 Ekon

-0.13

oya

-0.13

POSITIVE LOGITS

á»ķ

0.16

 depending

0.15

onder

0.15

essen

0.14

outu

0.14

aroo

0.14

 tact

0.14

 Wage

0.14

depending

0.14

otate

0.14

Activations Density 0.277%

references to conditional actions or requirements

No Comments

No Known Activations