INDEX

Explanations

information deemed pertinent or applicable to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

jur

-0.15

oen

-0.15

ÅĻe

-0.15

lio

-0.14

 Closure

-0.14

oppers

-0.14

aby

-0.13

jours

-0.13

iku

-0.13

rame

-0.13

POSITIVE LOGITS

posables

0.15

 Boyd

0.14

ional

0.14

retch

0.14

sembly

0.14

 ÄĳÃŃch

0.14

ekim

0.14

mpp

0.13

/dist

0.13

¸

0.13

Activations Density 0.010%

information deemed pertinent or applicable to various contexts

No Comments

No Known Activations