INDEX

Explanations

references to walls or wall-related concepts

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

ussen

-0.17

-git

-0.16

ects

-0.15

edis

-0.15

BarButtonItem

-0.15

etics

-0.15

ogue

-0.15

dle

-0.15

ãĤıãĤĬ

-0.15

sus

-0.14

POSITIVE LOGITS

avier

0.18

au

0.17

ang

0.17

ao

0.17

aud

0.16

ä¼į

0.16

-mounted

0.15

sWith

0.15

Activations Density 0.022%

references to walls or wall-related concepts

No Comments

No Known Activations