INDEX

Explanations

objects that have specific characteristics, materials, or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

urar

-0.15

ovice

-0.15

è»

-0.15

verture

-0.14

PARSE

-0.14

formats

-0.14

Formats

-0.14

 Ãºn

-0.13

tables

-0.13

Criterion

-0.13

POSITIVE LOGITS

 details

0.23

emb

0.23

 detailing

0.23

 handles

0.23

 writing

0.21

 detail

0.20

rid

0.20

 holes

0.20

 inscription

0.20

 patterns

0.19

Activations Density 0.350%

objects that have specific characteristics, materials, or features

No Comments

No Known Activations