INDEX

Explanations

specific medical or scientific terms related to conditions and their classifications

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

ÄĽÅ¾

-0.17

lap

-0.16

Lap

-0.15

Å¥

-0.15

 familiar

-0.15

Enumerable

-0.15

zym

-0.14

uments

-0.13

 familiarity

-0.13

sos

-0.13

POSITIVE LOGITS

readonly

0.17

outil

0.17

LOPT

0.15

 INST

0.14

oples

0.14

.IsSuccess

0.14

athlon

0.14

ä¸Ģäºº

0.14

_Lean

0.14

0.13

Activations Density 0.167%

specific medical or scientific terms related to conditions and their classifications

No Comments

No Known Activations