INDEX

Explanations

references to locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 west

-0.17

rine

-0.16

 east

-0.16

 ØºØ±Ø¨

-0.15

ument

-0.14

APER

-0.14

obs

-0.14

 western

-0.14

tings

-0.14

aper

-0.14

POSITIVE LOGITS

usat

0.15

onta

0.15

entai

0.15

bound

0.15

anj

0.14

ãĥ¼ãĥĩ

0.14

svc

0.14

anship

0.14

 Bought

0.13

 Seks

0.13

Activations Density 0.026%

references to locations and addresses

No Comments

No Known Activations