INDEX

Explanations

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ã¼gen

-0.15

ibble

-0.15

likes

-0.14

ihu

-0.14

caa

-0.14

lland

-0.13

pute

-0.13

oÅĽci

-0.13

OUN

-0.13

POSITIVE LOGITS

illo

0.17

URA

0.16

illos

0.15

Leod

0.14

ruz

0.14

Ø¶ÛĮ

0.14

sem

0.14

 Sanct

0.13

omorphic

0.13

 macro

0.13

Activations Density 0.016%

mathematical symbols and notation

No Comments

No Known Activations