INDEX

Explanations

expressions of opinion and emotional responses related to movies or stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ifr

-0.16

th

-0.15

orig

-0.15

iversit

-0.15

eka

-0.15

thr

-0.15

ropol

-0.14

ordo

-0.14

stor

-0.14

onso

-0.14

POSITIVE LOGITS

awah

0.18

Î½Î¬

0.15

InnerText

0.14

ç¾½

0.14

 INLINE

0.14

ä»¥æĿ¥

0.14

oted

0.14

imers

0.14

UTERS

0.14

Enumerator

0.14

Activations Density 0.141%

expressions of opinion and emotional responses related to movies or stories

No Comments

No Known Activations