INDEX

Explanations

mentions of "the" in various contexts

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

yntax

-0.16

enheim

-0.16

 Huck

-0.16

mae

-0.14

lingen

-0.14

orian

-0.14

 Sharp

-0.14

/event

-0.14

 Hunt

-0.14

chen

-0.14

POSITIVE LOGITS

 Predictor

0.16

bson

0.15

inet

0.15

taire

0.15

stery

0.15

erialize

0.14

aty

0.14

ailed

0.14

uhn

0.14

ferences

0.13

Activations Density 0.020%

mentions of "the" in various contexts

No Comments

No Known Activations