INDEX

Explanations

technical elements and specific identifiers in a written context

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

yped

-0.15

arih

-0.15

 nature

-0.15

YPES

-0.15

emma

-0.14

ifestyles

-0.14

ãĤ¦ãĥ³

-0.14

nature

-0.14

ogh

-0.13

POSITIVE LOGITS

EO

0.15

APER

0.15

ensch

0.15

 Redistribution

0.14

 Newton

0.14

opr

0.14

baz

0.14

gil

0.14

ifiable

0.14

aurus

0.14

Activations Density 0.013%

technical elements and specific identifiers in a written context

No Comments

No Known Activations