INDEX

Explanations

terms and references related to documents and file types

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

reeze

-0.15

ãĤŃãĥ¥

-0.15

prite

-0.15

orz

-0.15

atar

-0.14

çŃĨ

-0.14

 Ulus

-0.14

 Tunnel

-0.14

cratch

-0.13

aire

-0.13

POSITIVE LOGITS

Hav

0.16

ivant

0.14

 Valencia

0.14

lsen

0.14

 Audience

0.14

éĢ

0.13

AMA

0.13

 llam

0.13

 called

0.13

 ther

0.13

Activations Density 0.161%

terms and references related to documents and file types

No Comments

No Known Activations