INDEX

Explanations

instances of the word "set" across 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ibs

-0.15

Nug

-0.14

agna

-0.14

gang

-0.14

aine

-0.14

compan

-0.13

ination

-0.13

 Garn

-0.13

eman

-0.13

iders

-0.13

POSITIVE LOGITS

ucha

0.17

ìĿį

0.16

lish

0.16

tle

0.15

 multic

0.15

charm

0.15

amo

0.14

 Hakk

0.14

ocha

0.14

trys

0.14

Activations Density 0.042%

instances of the word "set" across various contexts

No Comments

No Known Activations