INDEX

Explanations

references to personal experiences and identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÏĥÏĦÎµ

-0.15

 Byron

-0.14

ISTER

-0.14

acking

-0.14

zego

-0.14

ÐµÑĢÐ¶Ð°Ð²

-0.13

 Bian

-0.13

tsl

-0.13

 coll

-0.13

ister

-0.13

POSITIVE LOGITS

idge

0.15

otor

0.14

RS

0.14

ãĥ¼ãĥĨ

0.14

 frequ

0.13

ql

0.13

bat

0.13

 hÆ°

0.13

@d

0.13

ë°Ģ

0.13

Activations Density 0.123%

references to personal experiences and identities

No Comments

No Known Activations