INDEX

Explanations

mentions of social media platforms and calls to follow or engage with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ToWorld

-0.16

lies

-0.15

ango

-0.15

ANGO

-0.15

','.

-0.14

Ã¡cil

-0.14

ORIGINAL

-0.14

 Bilim

-0.14

mtx

-0.14

ucha

-0.14

POSITIVE LOGITS

é§

0.17

ALES

0.15

lander

0.15

uben

0.14

 Camp

0.14

 Butler

0.14

 Singleton

0.14

0.13

Son

0.13

 sole

0.13

Activations Density 0.019%

mentions of social media platforms and calls to follow or engage with them

No Comments

No Known Activations