INDEX

Explanations

occurrences of the letter 'B' in 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ailles

-0.17

quier

-0.15

byss

-0.15

intree

-0.14

anax

-0.14

 Bols

-0.14

KT

-0.14

{*}

-0.14

ister

-0.14

 Hind

-0.14

POSITIVE LOGITS

ione

0.26

OLD

0.22

RITE

0.21

logs

0.20

 Corp

0.19

REAT

0.19

ioneer

0.18

icultural

0.18

IMA

0.18

Lab

0.18

Activations Density 0.027%

occurrences of the letter 'B' in various contexts

No Comments

No Known Activations