INDEX

Explanations

references to specific terms related to data structures and their management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ÃŃm

-0.19

ens

-0.16

imore

-0.15

arem

-0.15

orf

-0.15

onde

-0.14

/do

-0.14

bag

-0.14

_imm

-0.14

POSITIVE LOGITS

uzzi

0.17

mlink

0.15

 Crom

0.15

 Thickness

0.15

 Prospect

0.15

 reciprocal

0.14

VERR

0.14

$MESS

0.14

roc

0.14

avic

0.14

Activations Density 0.033%

references to specific terms related to data structures and their management

No Comments

No Known Activations