INDEX

Explanations

terms related to requirements and appropriateness for processes or items

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lyph

-0.16

_languages

-0.15

spi

-0.15

_LANGUAGE

-0.15

-0.14

 htons

-0.14

 Dispatch

-0.14

odel

-0.14

slot

-0.14

.getRoot

-0.14

POSITIVE LOGITS

ÑĥÐ·

0.17

endency

0.16

èĶµ

0.14

vid

0.14

astes

0.14

 McCl

0.14

ÏĦÏĥ

0.13

ç©¿

0.13

AGON

0.13

Activations Density 0.061%

terms related to requirements and appropriateness for processes or items

No Comments

No Known Activations