INDEX

Explanations

variations of the word "cleric" or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

venture

-0.15

lex

-0.15

 nerves

-0.14

 Police

-0.14

prov

-0.14

iram

-0.14

-expand

-0.14

illac

-0.14

WI

-0.14

rough

-0.13

POSITIVE LOGITS

ihan

0.19

TYPO

0.17

Typ

0.16

 cler

0.16

 Bout

0.16

stvo

0.15

kin

0.15

_typ

0.14

riba

0.14

ical

0.14

Activations Density 0.010%

variations of the word "cleric" or related terms

No Comments

No Known Activations