INDEX

Explanations

instances of the word "thus" and its variations, indicating conclusions or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

inya

-0.15

pk

-0.15

umba

-0.15

ationally

-0.15

ritch

-0.14

readcr

-0.14

ohn

-0.13

LÄ°

-0.13

lar

-0.13

sb

-0.13

POSITIVE LOGITS

forth

0.28

soever

0.18

nas

0.17

ly

0.16

Î²Î±

0.16

NAS

0.15

ìį¨

0.15

etta

0.15

acer

0.14

eto

0.14

Activations Density 0.024%

instances of the word "thus" and its variations, indicating conclusions or results

No Comments

No Known Activations