INDEX

Explanations

negative qualifiers that express limitation or contrast in a narrative

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

oba

-0.16

ulum

-0.15

ula

-0.15

overe

-0.14

alue

-0.14

ieren

-0.14

azon

-0.14

untas

-0.14

unt

-0.14

POSITIVE LOGITS

far

0.76

far

0.66

Far

0.60

FAR

0.59

Far

0.54

_far

0.49

by

0.46

 Ð´Ð°Ð»ÐµÐºÐ¾

0.45

 hardly

0.38

_FAR

0.36

Activations Density 0.178%

negative qualifiers that express limitation or contrast in a narrative

No Comments

No Known Activations