INDEX

Explanations

mentions of significant geographic or institutional names and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

nos

-0.17

_ttl

-0.15

Rek

-0.14

Gir

-0.14

roid

-0.14

VAS

-0.14

ãģ¨ãģĵãĤį

-0.14

aan

-0.14

UNET

-0.13

redict

-0.13

POSITIVE LOGITS

cke

0.16

ucer

0.16

ogh

0.14

 Guests

0.14

ogui

0.14

istine

0.14

ola

0.14

.GetResponse

0.14

odel

0.14

shal

0.14

Activations Density 0.043%

mentions of significant geographic or institutional names and concepts

No Comments

No Known Activations