INDEX

Explanations

references to academic journals and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

teness

-0.16

Ã¡ch

-0.16

loit

-0.16

utow

-0.15

loh

-0.15

etag

-0.15

stral

-0.15

genesis

-0.14

ÑĪÐ¸Ð½

-0.14

POSITIVE LOGITS

 Pruitt

0.16

igo

0.15

ekl

0.15

uries

0.14

sole

0.14

 Powers

0.14

 affecting

0.13

orm

0.13

 affect

0.13

inger

0.13

Activations Density 0.073%

references to academic journals and articles

No Comments

No Known Activations