INDEX

Explanations

phrases indicating existence or presence

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 ilet

-0.15

oler

-0.15

ÌĨ

-0.15

YYY

-0.15

wahl

-0.14

OLER

-0.14

GMEM

-0.14

LayoutConstraint

-0.14

POSITIVE LOGITS

uzzi

0.16

nah

0.15

Ð¾Ð²Ð°Ð»

0.15

uck

0.15

quis

0.15

rag

0.15

Î³Î¬

0.14

Mez

0.14

ouch

0.14

arger

0.14

Activations Density 0.134%

phrases indicating existence or presence

No Comments

No Known Activations