INDEX

Explanations

occurrences of the word "As" and variations of "ent" in context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

tuk

-0.15

ãģĤãģĴ

-0.15

MMdd

-0.14

uisse

-0.14

atables

-0.14

vyz

-0.14

uteur

-0.14

oulos

-0.14

ileaks

-0.13

etter

-0.13

POSITIVE LOGITS

anko

0.16

ghan

0.15

åį

0.14

anza

0.14

aba

0.14

iali

0.14

 ThreadPool

0.14

pects

0.14

lds

0.14

asco

0.14

Activations Density 0.054%

occurrences of the word "As" and variations of "ent" in context

No Comments

No Known Activations