INDEX

Explanations

structures and syntax in programming-related content

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

IMER

-0.17

llum

-0.17

imer

-0.15

ãĥ¼ãĥĢ

-0.15

ÃŃculo

-0.15

Ð¾Ð±ÑĭÑĤÐ¸

-0.14

verse

-0.14

setting

-0.14

akest

-0.13

actively

-0.13

POSITIVE LOGITS

omy

0.18

ãĥĥãĤ·ãĥ¥

0.15

panion

0.15

agn

0.14

hir

0.14

Nga

0.14

 Pitch

0.14

0.13

Activations Density 0.127%

structures and syntax in programming-related content

No Comments

No Known Activations