INDEX

Explanations

instances of the letter 'e'

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

sap

-0.15

inho

-0.15

orsi

-0.15

iddi

-0.15

la

-0.14

TA

-0.14

deg

-0.14

TT

-0.14

ieg

-0.14

POSITIVE LOGITS

pron

0.16

pte

0.15

Äįen

0.15

/resource

0.15

ptest

0.14

grily

0.14

ertino

0.14

ģ

0.14

vida

0.14

pter

0.14

Activations Density 0.042%

instances of the letter 'e'

No Comments

No Known Activations