INDEX

Explanations

names of individuals, specifically those with notable achievements or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oxy

-0.16

è·¡

-0.15

lor

-0.15

Kos

-0.14

ÏĦÎŃ

-0.14

ringe

-0.14

 Mini

-0.14

 incident

-0.14

esp

-0.14

phia

-0.14

POSITIVE LOGITS

ember

0.17

Î¼Î²

0.16

Forge

0.16

ØªÙħØ±

0.15

å¨

0.15

bove

0.14

 analog

0.14

á»ı

0.14

 Stations

0.14

StrictEqual

0.14

Activations Density 0.016%

names of individuals, specifically those with notable achievements or roles

No Comments

No Known Activations