INDEX

Explanations

punctuations and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

loe

-0.16

onation

-0.16

BN

-0.15

babel

-0.15

oriented

-0.14

iju

-0.14

oggler

-0.14

ingham

-0.14

readcrumb

-0.14

ials

-0.14

POSITIVE LOGITS

morgan

0.16

ADOR

0.16

apus

0.15

nbsp

0.15

Utc

0.15

#ad

0.14

<Props

0.14

ador

0.14

uo

0.14

-li

0.14

Activations Density 0.356%

punctuations and formatting

No Comments

No Known Activations