INDEX

Explanations

specific citations and references within a scholarly or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Mahon

-0.16

jong

-0.15

ooks

-0.15

æ

-0.15

adiens

-0.15

krom

-0.15

GMEM

-0.15

ÙĤØ¹

-0.14

trail

-0.14

aoke

-0.14

POSITIVE LOGITS

 Hast

0.20

Tib

0.19

ESL

0.18

 statist

0.17

 Pros

0.16

ple

0.16

Dia

0.15

abr

0.15

 Gentle

0.15

 Statistical

0.15

Activations Density 0.020%

specific citations and references within a scholarly or technical context

No Comments

No Known Activations