INDEX

Explanations

specific references to academic or formal texts in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ocal

-0.19

odel

-0.15

able

-0.14

 Grass

-0.14

 ØŃØµ

-0.14

ouston

-0.14

 grass

-0.14

ored

-0.14

plane

-0.14

POSITIVE LOGITS

/topics

0.15

stown

0.14

olid

0.14

ENTA

0.14

EP

0.14

BG

0.14

ACES

0.14

ÐµÑĢÐµ

0.14

_gem

0.14

çĭ¼

0.14

Activations Density 0.016%

specific references to academic or formal texts in various fields

No Comments

No Known Activations