INDEX

Explanations

quotes and references in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

azo

-0.15

ginas

-0.15

ãģ°ãģĭãĤĬ

-0.15

oyo

-0.15

bler

-0.14

berger

-0.14

ilst

-0.14

chwitz

-0.14

rone

-0.14

udge

-0.14

POSITIVE LOGITS

bon

0.14

 rational

0.14

nets

0.13

 Myth

0.13

-haspopup

0.13

fur

0.13

 equal

0.13

bell

0.13

uren

0.13

ideon

0.12

Activations Density 0.069%

quotes and references in text

No Comments

No Known Activations