INDEX

Explanations

references to the year "195"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.17

isko

-0.16

usc

-0.14

ocols

-0.14

ivo

-0.14

/trunk

-0.14

IVA

-0.14

rÃ¡l

-0.14

iddi

-0.14

POSITIVE LOGITS

arden

0.16

arness

0.15

åĳĬ

0.14

lse

0.14

emark

0.14

ptron

0.14

 Cush

0.13

à¥įà¤µà¤µ

0.13

lÃ¡d

0.13

fis

0.13

Activations Density 0.008%

references to the year "195"

No Comments

No Known Activations