INDEX

Explanations

the presence of specific phrases or terms related to entertainment or media

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

hea

-0.15

verty

-0.14

atif

-0.14

-settings

-0.14

anas

-0.14

lap

-0.14

 tavs

-0.13

ÎºÎ·ÏĤ

-0.13

Hook

-0.13

../../../

-0.13

POSITIVE LOGITS

ongyang

0.17

 Balk

0.16

0.15

/API

0.14

%D

0.14

akra

0.14

iez

0.13

ibili

0.13

_ANDROID

0.13

urious

0.13

Activations Density 0.000%

the presence of specific phrases or terms related to entertainment or media

No Comments

No Known Activations