INDEX

Explanations

references to individual responses and agreements in textual discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

nev

-0.17

EXIT

-0.15

 deps

-0.15

 EXIT

-0.14

dep

-0.14

mut

-0.14

ALI

-0.14

BOVE

-0.13

 Alien

-0.13

EXTERN

-0.13

POSITIVE LOGITS

 interven

0.16

 replies

0.15

onz

0.14

Ð¶ÐµÐ½ÑĮ

0.14

response

0.14

iry

0.14

orta

0.14

nze

0.14

jax

0.14

acher

0.14

Activations Density 0.195%

references to individual responses and agreements in textual discussions

No Comments

No Known Activations