INDEX

Explanations

occurrences of the prefix "dis" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Niet

-0.15

tempts

-0.14

erspective

-0.14

onen

-0.14

IED

-0.14

Ñī

-0.14

action

-0.14

tir

-0.14

abb

-0.14

perience

-0.14

POSITIVE LOGITS

Dis

0.19

crete

0.17

Ø±Ø¨ÛĮ

0.17

dis

0.17

 Ticaret

0.16

covery

0.16

ney

0.16

-dis

0.16

 Ð´Ð¸Ñģ

0.16

.dis

0.16

Activations Density 0.028%

occurrences of the prefix "dis" in various forms

No Comments

No Known Activations