INDEX

Explanations

programming-related syntax and structure, particularly in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

oric

-0.18

ure

-0.15

uan

-0.15

urate

-0.15

inder

-0.15

 isNaN

-0.14

Hunter

-0.14

izzo

-0.14

apt

-0.14

POSITIVE LOGITS

.hy

0.16

_reporting

0.15

annes

0.15

elter

0.15

egl

0.15

åĨµ

0.15

mland

0.14

woff

0.14

 opposition

0.14

å¯

0.14

Activations Density 0.174%

programming-related syntax and structure, particularly in code snippets

No Comments

No Known Activations