INDEX

Explanations

instances of the word 'em' and its variations, indicating a focus on character dialogue or colloquial expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

keit

-0.18

orp

-0.17

eum

-0.17

ettes

-0.15

avad

-0.15

oq

-0.15

ous

-0.15

ToProps

-0.14

,rp

-0.14

ats

-0.14

POSITIVE LOGITS

eps

0.19

elf

0.18

ep

0.18

perature

0.18

kes

0.18

elm

0.17

gth

0.17

ç¾

0.15

ched

0.15

ninger

0.15

Activations Density 0.039%

instances of the word 'em' and its variations, indicating a focus on character dialogue or colloquial expressions

No Comments

No Known Activations