INDEX

Explanations

names and terms related to language and pronunciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

anonymous

-0.16

rary

-0.16

eph

-0.15

 rhet

-0.15

istar

-0.15

ktop

-0.14

anio

-0.14

raquo

-0.14

anford

-0.14

-Language

-0.14

POSITIVE LOGITS

 spell

0.54

spell

0.46

 spelling

0.45

 Spell

0.45

Spell

0.44

pron

0.42

 spelled

0.40

 pronounce

0.39

 pron

0.39

 SPELL

0.38

Activations Density 0.186%

names and terms related to language and pronunciation

No Comments

No Known Activations

names and terms related to language and pronunciation

No Comments

No Known Activations