INDEX

Explanations

references to health-related products or interventions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

DOMNode

-0.16

LError

-0.15

pragma

-0.14

æģµ

-0.14

hardt

-0.14

idades

-0.13

allel

-0.13

éģķãģĦ

-0.13

 Revenge

-0.13

hawk

-0.13

POSITIVE LOGITS

idos

0.16

alf

0.15

ire

0.15

ublik

0.15

isel

0.15

bench

0.14

aal

0.13

posal

0.13

 condition

0.13

 blobs

0.13

Activations Density 0.262%

references to health-related products or interventions

No Comments

No Known Activations