INDEX

Explanations

references to time and specific events

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

estar

-0.16

@Module

-0.15

blas

-0.15

-0.14

sans

-0.14

bable

-0.14

ongs

-0.14

anio

-0.14

lest

-0.14

 Portions

-0.14

POSITIVE LOGITS

WithString

0.16

eli

0.15

culus

0.15

 TestUtils

0.14

STANCE

0.14

ENCIL

0.14

ellen

0.13

 ká»

0.13

borough

0.13

_LAYOUT

0.13

Activations Density 0.046%

references to time and specific events

No Comments

No Known Activations