INDEX

Explanations

references to research and topic discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

enia

-0.16

tra

-0.15

lein

-0.15

%;">

-0.14

unkt

-0.14

inha

-0.14

ĥn

-0.14

Ð°ÑģÑĤÐ¸

-0.14

nak

-0.14

tar

-0.14

POSITIVE LOGITS

acades

0.16

odate

0.16

hod

0.16

DEX

0.14

emey

0.14

rana

0.14

/topic

0.14

_exc

0.14

0.13

SPA

0.13

Activations Density 0.003%

references to research and topic discussions

No Comments

No Known Activations

references to research and topic discussions

No Comments

No Known Activations