INDEX

Explanations

dates and specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Ð³Ð¾ÑĤ

-0.14

serter

-0.14

TRIES

-0.14

é¡ĺãģĦ

-0.14

kening

-0.14

ruk

-0.14

ongoose

-0.14

otron

-0.14

sense

-0.13

POSITIVE LOGITS

anda

0.16

asso

0.14

asal

0.14

unte

0.14

zure

0.14

 Loves

0.14

 Merr

0.13

awy

0.13

unday

0.13

pect

0.13

Activations Density 0.099%

dates and specific years

No Comments

No Known Activations