INDEX

Explanations

occurrences of the word "place" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

elage

-0.19

rez

-0.17

rape

-0.16

thin

-0.16

atra

-0.16

emoc

-0.15

rr

-0.15

lyn

-0.15

aries

-0.15

ly

-0.15

POSITIVE LOGITS

bos

0.29

HOLDER

0.23

OfBirth

0.21

idon

0.21

holders

0.18

able

0.18

ful

0.17

over

0.17

upon

0.17

picker

0.17

Activations Density 0.072%

occurrences of the word "place" in various contexts

No Comments

No Known Activations