INDEX

Explanations

occurrences of the letter 'm' 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ninger

-0.19

ut

-0.16

daq

-0.15

bench

-0.14

urd

-0.14

ben

-0.14

exels

-0.14

äº¬

-0.14

elim

-0.14

utex

-0.14

POSITIVE LOGITS

0.17

IVEN

0.17

ippo

0.15

radu

0.15

adlo

0.15

ãģĤãĤĬ

0.15

.MixedReality

0.15

incinn

0.15

Ere

0.14

hape

0.14

Activations Density 0.024%

occurrences of the letter 'm' in various contexts

No Comments

No Known Activations