INDEX

Explanations

names or terms related to locations or places associated with food or cuisine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ymous

-0.17

mdi

-0.15

issen

-0.14

orsi

-0.14

ourt

-0.14

_basename

-0.14

emente

-0.14

ÐµÑĦ

-0.14

 Ø§ÙĦØ¬ÙĨ

-0.14

isci

-0.13

POSITIVE LOGITS

ÑģÐºÐ»Ð°Ð´

0.16

 kháº©u

0.15

ertino

0.15

aghan

0.15

 comput

0.15

 Drum

0.14

tid

0.14

ragon

0.14

 convict

0.14

sworth

0.14

Activations Density 0.037%

names or terms related to locations or places associated with food or cuisine

No Comments

No Known Activations