INDEX

Explanations

terms related to standards and specifications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

irl

-0.14

 everything

-0.14

 other

-0.14

 overall

-0.14

.xyz

-0.13

_##

-0.13

 anything

-0.13

 obviously

-0.13

aden

-0.13

POSITIVE LOGITS

inic

0.15

onga

0.15

LEAR

0.14

ELY

0.14

 adlÄ±

0.13

DU

0.13

ripe

0.13

azole

0.13

ucene

0.13

Floor

0.13

Activations Density 0.156%

terms related to standards and specifications in various contexts

No Comments

No Known Activations