INDEX

Explanations

symbols and special characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

skirts

-0.18

orny

-0.16

sburg

-0.16

baugh

-0.15

arro

-0.15

ovich

-0.15

mentions

-0.15

sig

-0.15

andles

-0.14

mention

-0.14

POSITIVE LOGITS

³

0.18

ears

0.17

Ĭ

0.16

İ

0.16

pra

0.15

Ń

0.15

seealso

0.15

geometry

0.14

º

0.14

Ŀ

0.14

Activations Density 0.007%

symbols and special characters

No Comments

No Known Activations