INDEX

Explanations

phrases involving identity and self-description

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

 Ones

-0.16

ipy

-0.16

-html

-0.15

 ones

-0.15

SCI

-0.14

_neurons

-0.14

annotations

-0.14

Orm

-0.14

athi

-0.14

 Hann

-0.13

POSITIVE LOGITS

ailles

0.15

ysz

0.15

æħ§

0.15

hÃ¡

0.14

asad

0.14

ovice

0.14

bridge

0.14

hurst

0.13

iamond

0.13

Activations Density 0.609%

phrases involving identity and self-description

No Comments

No Known Activations