INDEX

Explanations

technical terms and programming-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

eniz

-0.17

radient

-0.17

á»§

-0.15

zte

-0.15

Ø±Ø¯

-0.15

 lá»¥c

-0.15

ãĥĥãĤ·ãĥ¥

-0.14

rts

-0.14

 Instructions

-0.14

airs

-0.14

POSITIVE LOGITS

 Arrow

0.15

istol

0.15

size

0.15

TeX

0.14

munition

0.14

leur

0.13

Arrow

0.13

Î²Î¬

0.13

quo

0.13

ObjectContext

0.13

Activations Density 0.001%

technical terms and programming-related concepts

No Comments

No Known Activations