INDEX

Explanations

phrases reflecting past experiences and actions

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

adele

-0.16

 Criterion

-0.16

InnerText

-0.15

ileo

-0.14

ÏģÏħ

-0.14

Criterion

-0.14

_criteria

-0.14

 Criteria

-0.14

ovny

-0.14

ette

-0.14

POSITIVE LOGITS

endants

0.16

hone

0.16

utow

0.15

 elsewhere

0.15

 Relatives

0.14

 giÃł

0.14

 Already

0.14

_PAIR

0.14

 previously

0.14

ysi

0.14

Activations Density 0.299%

phrases reflecting past experiences and actions

No Comments

No Known Activations