INDEX

Explanations

numerical identifiers and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.19

 Stanton

-0.15

olie

-0.14

aina

-0.14

tom

-0.14

æĤ

-0.14

 Dipl

-0.14

HN

-0.13

chen

-0.13

sey

-0.13

POSITIVE LOGITS

kke

0.15

instr

0.15

asco

0.14

_TRUNC

0.14

sst

0.14

vect

0.14

Ã£ng

0.14

 themselves

0.14

Ħ

0.14

si

0.13

Activations Density 0.003%

numerical identifiers and locations

No Comments

No Known Activations