INDEX

Explanations

programming syntax, specifically related to code structure and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oir

-0.15

map

-0.15

bang

-0.14

.getSeconds

-0.13

<Map

-0.13

Selectors

-0.13

/map

-0.13

Ø´Øª

-0.13

åł

-0.13

InThe

-0.13

POSITIVE LOGITS

.IContainer

0.16

ArrayOf

0.16

ueba

0.16

asan

0.16

agues

0.15

ingo

0.15

uset

0.15

elm

0.15

ektiv

0.15

okino

0.14

Activations Density 0.004%

programming syntax, specifically related to code structure and formatting

No Comments

No Known Activations