INDEX

Explanations

instances of the word "reveal" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ello

-0.16

elier

-0.16

estre

-0.15

olan

-0.15

à¯įà®

-0.15

 Unidos

-0.15

itten

-0.14

-Ñħ

-0.14

igu

-0.14

SSIP

-0.14

POSITIVE LOGITS

 secrets

0.27

 details

0.23

ry

0.21

 Secrets

0.20

why

0.20

 hidden

0.19

how

0.18

iance

0.18

tid

0.18

ments

0.17

Activations Density 0.031%

instances of the word "reveal" and its variations

No Comments

No Known Activations