INDEX

Explanations

code-related references to paths and file operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

FFE

-0.16

íķĺìĭľ

-0.15

abbo

-0.14

åĦĢ

-0.14

amac

-0.14

 semiclass

-0.14

iesen

-0.14

ritis

-0.14

dera

-0.14

 ctype

-0.13

POSITIVE LOGITS

(:,:,

0.16

uckle

0.15

[~,

0.15

0.14

 Kiss

0.14

ael

0.14

Activations Density 0.800%

code-related references to paths and file operations

No Comments

No Known Activations