INDEX

Explanations

programming syntax and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

aname

-0.16

 Irving

-0.14

ihn

-0.14

lijah

-0.14

anos

-0.14

Ð·Ð²

-0.14

.club

-0.14

ichte

-0.14

flen

-0.13

andom

-0.13

POSITIVE LOGITS

ngo

0.15

ensa

0.15

nger

0.15

HL

0.15

umba

0.15

HL

0.14

atro

0.14

gest

0.14

emer

0.14

 Lloyd

0.14

Activations Density 0.116%

programming syntax and structure

No Comments

No Known Activations