INDEX

Explanations

references to programming functions and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ãģįãģŁ

-0.21

à¯į

-0.18

illin

-0.17

à¯įà®

-0.17

Ð½ÑĤ

-0.16

ovich

-0.16

fty

-0.16

Øª

-0.15

ect

-0.15

nte

-0.15

POSITIVE LOGITS

iard

0.17

ingly

0.16

aging

0.16

ington

0.15

ler

0.15

rÃ¡n

0.15

lesi

0.15

engers

0.14

MAND

0.14

Activations Density 1.309%

references to programming functions and variables

No Comments

No Known Activations