INDEX

Explanations

programming-related keywords and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Gen

-0.16

gen

-0.15

 Goldberg

-0.15

otch

-0.15

eea

-0.14

tera

-0.14

ille

-0.14

Ãªs

-0.14

ype

-0.13

POSITIVE LOGITS

PIX

0.15

 Leban

0.15

iki

0.15

Ð¾Ð´Ð¾

0.15

bsd

0.15

ogi

0.15

ÑģÑĤÐ¸Ð½

0.14

 Seymour

0.14

çĻº

0.14

Activations Density 0.173%

programming-related keywords and structure

No Comments

No Known Activations