INDEX

Explanations

comment indicators in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ti

-0.15

inou

-0.15

ãģįãģŁ

-0.15

olt

-0.14

Iss

-0.14

tip

-0.14

ence

-0.14

á»ķi

-0.14

per

-0.14

tw

-0.14

POSITIVE LOGITS

0.19

0.17

ies

0.16

0.15

//{{

0.15

.literal

0.14

roots

0.14

arra

0.14

Activations Density 0.018%

comment indicators in code

No Comments

No Known Activations