INDEX

Explanations

references to visual elements and media representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

oland

-0.16

icol

-0.15

ulares

-0.14

.fun

-0.14

Dit

-0.14

 intermedi

-0.13

.nr

-0.13

 indul

-0.13

obar

-0.13

 :↵↵

-0.13

POSITIVE LOGITS

anc

0.15

ewriter

0.14

olute

0.14

omanip

0.14

 Kore

0.14

Ä©a

0.13

 Äĳá»ķ

0.13

seo

0.13

altet

0.13

eve

0.13

Activations Density 0.077%

references to visual elements and media representation

No Comments

No Known Activations