INDEX

Explanations

statements of factual assertions or descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

isman

-0.17

uture

-0.15

ide

-0.14

ongan

-0.14

idan

-0.14

ish

-0.14

_tac

-0.14

onga

-0.14

decorators

-0.14

omb

-0.14

POSITIVE LOGITS

why

0.23

why

0.21

 incident

0.20

 INCIDENT

0.17

 Incident

0.16

btw

0.16

.af

0.15

/sdk

0.15

Î¼Î¬

0.14

ä¸ºä»Ģä¹Ī

0.14

Activations Density 0.107%

statements of factual assertions or descriptors

No Comments

No Known Activations