INDEX

Explanations

references to literature, specifically novels and plays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

yor

-0.16

utzer

-0.14

sheet

-0.14

 issue

-0.14

ASHBOARD

-0.14

sel

-0.14

rikes

-0.14

onom

-0.14

 Curt

-0.14

POSITIVE LOGITS

-length

0.18

ice

0.15

ito

0.15

ÐºÐ¾ÑĤ

0.15

aisy

0.15

cko

0.14

mente

0.14

merge

0.14

cdecl

0.14

RelativeTo

0.14

Activations Density 0.028%

references to literature, specifically novels and plays

No Comments

No Known Activations