INDEX

Explanations

phrases related to being trapped or stuck in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

@$_

-0.15

arily

-0.15

Ð·Ñĥ

-0.14

VOICE

-0.14

æĻ

-0.14

ekler

-0.14

 ballistic

-0.14

inear

-0.14

TMP

-0.14

POSITIVE LOGITS

 stuck

0.18

angl

0.16

 ciclo

0.15

 cycle

0.15

celik

0.15

sticky

0.15

ansa

0.15

Vie

0.15

esse

0.14

 cycles

0.14

Activations Density 0.063%

phrases related to being trapped or stuck in various contexts

No Comments

No Known Activations