INDEX

Explanations

references to the pronoun "it."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ofire

-0.17

shr

-0.15

ailles

-0.15

uzey

-0.15

shr

-0.15

oload

-0.14

pq

-0.14

anax

-0.14

eniable

-0.14

ranÃŃ

-0.14

POSITIVE LOGITS

orden

0.16

asca

0.16

 cheat

0.15

bow

0.15

vet

0.14

aml

0.14

erro

0.14

çĶ²

0.14

Ted

0.14

ord

0.14

Activations Density 0.213%

references to the pronoun "it."

No Comments

No Known Activations