INDEX

Explanations

terms related to legal jurisdiction or authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

bons

-0.16

getAs

-0.15

urb

-0.15

.structure

-0.15

aska

-0.14

ijd

-0.14

izzie

-0.14

ohl

-0.14

anol

-0.14

 tiener

-0.14

POSITIVE LOGITS

éı¡

0.15

pcion

0.15

Fol

0.14

Eg

0.14

ainer

0.13

acent

0.13

inta

0.13

bate

0.13

UA

0.13

Activations Density 0.015%

terms related to legal jurisdiction or authority

No Comments

No Known Activations