INDEX

Explanations

colons used to introduce lists or tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

otts

-0.16

_PP

-0.14

smarty

-0.14

Woj

-0.14

mania

-0.14

 kanal

-0.14

avin

-0.13

.paths

-0.13

alia

-0.13

endance

-0.13

POSITIVE LOGITS

resco

0.17

jeme

0.15

ulers

0.15

jun

0.15

riere

0.14

Jun

0.14

.Toolkit

0.14

ifes

0.14

ych

0.14

TC

0.14

Activations Density 0.005%

colons used to introduce lists or tags

No Comments

No Known Activations