INDEX

Explanations

references to external links or sources

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

idlo

-0.15

_Entry

-0.14

 mess

-0.14

 forState

-0.14

artner

-0.14

dle

-0.14

pub

-0.14

çłĤ

-0.14

UBLIC

-0.13

ordes

-0.13

POSITIVE LOGITS

 Pickup

0.16

uforia

0.15

ilities

0.14

/internal

0.14

 geile

0.14

aghan

0.14

 dara

0.14

à¸´à¹Ĥà¸¥

0.13

Activations Density 0.003%

references to external links or sources

No Comments

No Known Activations