INDEX

Explanations

specific geographical and scientific terminology related to regions and urban characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.mdl

-0.15

 skies

-0.14

atabase

-0.14

.obtain

-0.13

 Harm

-0.13

aza

-0.13

adden

-0.13

 pestic

-0.13

.self

-0.13

_accessible

-0.13

POSITIVE LOGITS

Rap

0.16

onom

0.15

ourt

0.15

unsupported

0.15

0.14

forward

0.14

jun

0.14

Fal

0.14

seys

0.14

Gate

0.14

Activations Density 0.207%

specific geographical and scientific terminology related to regions and urban characteristics

No Comments

No Known Activations