INDEX

Explanations

references to people and relationships within various contexts

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

="../../../

-0.17

ish

-0.16

emie

-0.16

addon

-0.15

suo

-0.13

Lip

-0.13

Å¾i

-0.13

ieu

-0.13

ihan

-0.13

UBL

-0.12

POSITIVE LOGITS

own

0.35

’

0.31

Own

0.21

 ability

0.19

 latest

0.18

own

0.18

’)

0.18

uffers

0.17

 main

0.17

Activations Density 0.400%

references to people and relationships within various contexts

No Comments

No Known Activations