INDEX

Explanations

attributions of statements or opinions by various individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

_fsm

-0.15

viso

-0.14

ãĥĥãĤ«ãĥ¼

-0.14

Ð¼ÐµÑĩ

-0.14

 xmlns

-0.14

/entities

-0.13

-transitional

-0.13

EMP

-0.13

POSITIVE LOGITS

_opts

0.15

onis

0.14

creasing

0.13

entic

0.13

eam

0.13

ContextHolder

0.13

imli

0.13

/TT

0.13

ipi

0.13

ails

0.13

Activations Density 0.015%

attributions of statements or opinions by various individuals

No Comments

No Known Activations

attributions of statements or opinions by various individuals

No Comments

No Known Activations