INDEX

Explanations

instances of the word "from," indicating discussions of origin or background

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

fare

-0.15

riel

-0.14

YP

-0.14

odo

-0.14

olo

-0.14

lesh

-0.14

-0.13

POSITIVE LOGITS

linky

0.16

pig

0.15

à¥Įà¤¤

0.15

emachine

0.14

cycle

0.14

orris

0.14

RULE

0.14

uez

0.14

xiety

0.14

AndWait

0.14

Activations Density 0.021%

instances of the word "from," indicating discussions of origin or background

No Comments

No Known Activations