INDEX

Explanations

occurrences of the word "Hill" and its variations 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

yne

-0.16

kla

-0.16

vais

-0.16

sak

-0.15

ecz

-0.15

ooke

-0.14

icha

-0.14

samp

-0.14

avian

-0.14

POSITIVE LOGITS

side

0.48

iard

0.43

top

0.38

crest

0.31

arious

0.30

iards

0.25

ides

0.24

ier

0.24

ary

0.23

bill

0.23

Activations Density 0.012%

occurrences of the word "Hill" and its variations in various contexts

No Comments

No Known Activations