INDEX

Explanations

words related to disruption and conflicts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rays

-0.15

leÅŁ

-0.14

ÑĩÐ°Ñģ

-0.14

perience

-0.14

ition

-0.14

smooth

-0.14

enu

-0.14

CHAT

-0.13

hind

-0.13

POSITIVE LOGITS

ellaneous

0.19

naire

0.16

emean

0.16

ettes

0.16

aire

0.15

rael

0.15

ned

0.14

ly

0.14

omics

0.14

agara

0.14

Activations Density 0.121%

words related to disruption and conflicts

No Comments

No Known Activations