INDEX

Explanations

references to specific links and guidelines for accessing content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

adle

-0.15

loor

-0.15

ninger

-0.15

atron

-0.14

TY

-0.14

Ð¼Ð¾ÑĤÑĢÐµÑĤÑĮ

-0.14

 ØªÙĪØ±

-0.13

issen

-0.13

ì§¸

-0.13

SCII

-0.13

POSITIVE LOGITS

0.14

 voxel

0.14

edly

0.14

.vaadin

0.14

 Benedict

0.14

/material

0.13

 Impl

0.13

olla

0.13

.Scan

0.13

 ÙĨØ³

0.13

Activations Density 0.000%

references to specific links and guidelines for accessing content

No Comments

No Known Activations