INDEX

Explanations

occurrences of the word "icon" and its variations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

æ²

-0.17

à¸´à¸ŀ

-0.17

MMdd

-0.15

bral

-0.15

sonian

-0.15

Î¸ÎµÎ½

-0.14

pline

-0.14

lÃŃ

-0.14

ertas

-0.14

 neger

-0.14

POSITIVE LOGITS

nect

0.22

oc

0.19

ic

0.19

odule

0.18

omidou

0.18

ically

0.18

atural

0.17

ography

0.17

ocl

0.17

ëħķ

0.17

Activations Density 0.009%

occurrences of the word "icon" and its variations in the text

No Comments

No Known Activations