INDEX

Explanations

variations of the word "habitat."

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

ÑıÐ½

-0.19

isha

-0.15

elage

-0.15

à¸¢à¸§

-0.14

ÑĶÐ²

-0.14

 ObrÃ¡zky

-0.14

 supper

-0.14

xFFF

-0.13

onz

-0.13

idar

-0.13

POSITIVE LOGITS

qv

0.16

/apt

0.16

iale

0.15

 Merr

0.14

 Banc

0.14

antu

0.14

mue

0.14

 secre

0.14

 Tracking

0.14

_secure

0.13

Activations Density 0.021%

variations of the word "habitat."

No Comments

No Known Activations