INDEX

Explanations

references to organization-related terms or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

csr

-0.15

 è¡

-0.15

zew

-0.15

AuthProvider

-0.15

onica

-0.14

vana

-0.14

Ð¾Ð±Ð°

-0.14

rana

-0.13

cil

-0.13

izzard

-0.13

POSITIVE LOGITS

.slf

0.17

Apache

0.16

-json

0.15

org

0.15

inal

0.14

uhl

0.14

 apache

0.14

QRST

0.14

astic

0.14

ãĥĨãĥ«

0.14

Activations Density 0.012%

references to organization-related terms or entities

No Comments

No Known Activations