INDEX

Explanations

terms related to assurance and confirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

)?$

-0.14

rahim

-0.14

_PHP

-0.14

_named

-0.14

disposing

-0.14

 Horny

-0.14

iec

-0.13

oust

-0.13

udios

-0.13

zew

-0.13

POSITIVE LOGITS

olated

0.16

amas

0.15

eter

0.15

olation

0.15

-Za

0.15

ff

0.14

ç½

0.14

obo

0.14

 actionTypes

0.14

 Cummings

0.14

Activations Density 0.008%

terms related to assurance and confirmation

No Comments

No Known Activations