INDEX

Explanations

formal identifiers and classification terms related to people or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 forth

-0.16

HI

-0.16

azard

-0.14

oral

-0.14

ughters

-0.14

hap

-0.14

ors

-0.14

fallback

-0.13

_HI

-0.13

POSITIVE LOGITS

hest

0.15

ieux

0.15

 Stam

0.15

engin

0.15

stvo

0.15

iloc

0.15

é»Ħ

0.14

adÃŃ

0.14

ycl

0.14

AMIL

0.14

Activations Density 0.040%

formal identifiers and classification terms related to people or organizations

No Comments

No Known Activations