INDEX

Explanations

the word "he" and its variations

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

TOTYPE

-0.15

 Marshall

-0.15

ungal

-0.14

Ãºsqueda

-0.14

ÑĥÐº

-0.14

Tah

-0.14

totals

-0.14

onu

-0.14

 addCriterion

-0.14

_ttl

-0.13

POSITIVE LOGITS

poon

0.15

ãĥ³ãĥĪ

0.15

hausen

0.15

lius

0.14

çĮ

0.14

ienie

0.14

atron

0.14

reon

0.14

atre

0.14

.Generated

0.14

Activations Density 0.016%

the word "he" and its variations

No Comments

No Known Activations