INDEX

Explanations

occurrences of the word "blank" and its variations, indicating a focus on emptiness or absence

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

ekil

-0.18

ropic

-0.17

rious

-0.16

strict

-0.16

leigh

-0.16

gings

-0.15

antas

-0.15

wend

-0.15

zan

-0.15

rians

-0.15

POSITIVE LOGITS

eted

0.39

eting

0.37

 slate

0.30

ety

0.27

 Slate

0.25

 canv

0.22

enburg

0.21

ens

0.20

 Blank

0.20

 canvas

0.20

Activations Density 0.007%

occurrences of the word "blank" and its variations, indicating a focus on emptiness or absence

No Comments

No Known Activations