INDEX

Explanations

customer-focused language relating to business services and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ESH

-0.17

obe

-0.16

 Weiner

-0.16

oding

-0.15

rg

-0.15

_RENDERER

-0.15

scope

-0.14

segue

-0.14

igh

-0.14

uni

-0.14

POSITIVE LOGITS

CT

0.17

 ours

0.15

izzly

0.15

CTX

0.14

 reordered

0.14

cpy

0.14

plen

0.14

actor

0.13

cion

0.13

Activations Density 0.212%

customer-focused language relating to business services and support

No Comments

No Known Activations