INDEX

Explanations

notions of comparison and sequencing within arguments or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ifndef

-0.15

_firestore

-0.14

oods

-0.13

INGER

-0.13

pray

-0.13

ofs

-0.13

uger

-0.13

itty

-0.13

ula

-0.13

POSITIVE LOGITS

-Sah

0.15

 Crist

0.15

usher

0.14

lexer

0.14

Bol

0.14

 Convention

0.14

emez

0.14

aler

0.13

frag

0.13

Activations Density 0.637%

notions of comparison and sequencing within arguments or explanations

No Comments

No Known Activations