INDEX

Explanations

descriptions of visual elements and graphics in media

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

amer

-0.14

ules

-0.14

estre

-0.14

_STAT

-0.14

xba

-0.14

-0.13

estion

-0.13

 Mons

-0.13

 Scenario

-0.13

POSITIVE LOGITS

Ĵáŀ

0.16

ãĥ¥ãĥ¼

0.16

Dud

0.15

SWEP

0.15

 *)((

0.15

 PROGMEM

0.15

iá»ĩu

0.14

SGlobal

0.14

_ATOMIC

0.14

 pageInfo

0.13

Activations Density 0.066%

descriptions of visual elements and graphics in media

No Comments

No Known Activations