INDEX

Explanations

references to visuals or images in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Portrait

-0.14

,ll

-0.14

-twitter

-0.14

owie

-0.14

 drawers

-0.13

_PTR

-0.13

 Lesser

-0.13

.getHeader

-0.13

chor

-0.13

POSITIVE LOGITS

 shot

0.18

 looks

0.18

oglob

0.18

Looks

0.17

looks

0.17

 shots

0.17

 Looks

0.17

 shown

0.15

 look

0.15

 Shot

0.15

Activations Density 0.244%

references to visuals or images in context

No Comments

No Known Activations