INDEX

Explanations

proper nouns related to individuals, brands, 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ëĿ½

-0.14

_Osc

-0.14

TargetException

-0.14

ARGS

-0.13

odv

-0.13

 Jenkins

-0.13

 nhiÃªn

-0.13

 serialVersionUID

-0.13

roker

-0.13

.spatial

-0.13

POSITIVE LOGITS

anza

0.16

abox

0.15

anz

0.15

apol

0.14

pa

0.14

ham

0.14

antry

0.14

pie

0.14

onom

0.13

ael

0.13

Activations Density 0.879%

proper nouns related to individuals, brands, or organizations

No Comments

No Known Activations