INDEX

Explanations

occurrences of adjectives and adverbs that describe characteristics or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Bach

-0.15

ebin

-0.14

ussed

-0.14

esModule

-0.14

ewolf

-0.14

idon

-0.14

idel

-0.14

imar

-0.14

 Plum

-0.13

lish

-0.13

POSITIVE LOGITS

rze

0.15

izi

0.15

rÅ¾

0.14

Synopsis

0.14

isz

0.14

ady

0.13

OLA

0.13

ë¦

0.13

boa

0.13

 GÃ¶r

0.13

Activations Density 0.178%

occurrences of adjectives and adverbs that describe characteristics or actions

No Comments

No Known Activations