INDEX

Explanations

various definitions or terms related to specific concepts

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

aji

-0.15

Grammar

-0.15

ukkit

-0.15

idge

-0.15

STA

-0.14

utin

-0.14

-contrib

-0.14

prus

-0.14

-valu

-0.14

_via

-0.14

POSITIVE LOGITS

forge

0.16

cker

0.16

ONY

0.15

rag

0.15

ritis

0.15

 Kang

0.14

CKER

0.14

 ç¯

0.14

dle

0.14

 provinc

0.14

Activations Density 0.017%

various definitions or terms related to specific concepts

No Comments

No Known Activations