INDEX

Explanations

phrases and concepts related to actions, processes, and assessments of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

onomy

-0.19

/Foundation

-0.16

geist

-0.15

èĵ

-0.14

ere

-0.14

instanc

-0.14

rip

-0.14

_effects

-0.13

nt

-0.13

onta

-0.13

POSITIVE LOGITS

 Lonely

0.15

etur

0.15

.Interfaces

0.15

ilden

0.14

ewood

0.14

urd

0.14

THEN

0.14

icas

0.14

ATRIX

0.14

 Cannon

0.14

Activations Density 0.013%

phrases and concepts related to actions, processes, and assessments of information

No Comments

No Known Activations