INDEX

Explanations

mentions of the name "Nad" and its variations, indicating a focus on a specific individual or character within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÎŃÏģÎ³

-0.17

outh

-0.15

Ãªt

-0.14

aid

-0.14

teÅŁ

-0.14

orio

-0.14

esi

-0.14

sis

-0.14

ister

-0.13

lopen

-0.13

POSITIVE LOGITS

åºŃ

0.16

agus

0.16

ĽĪ

0.15

Nad

0.15

uno

0.15

pecies

0.14

posite

0.14

ossier

0.14

 Wend

0.14

Activations Density 0.017%

mentions of the name "Nad" and its variations, indicating a focus on a specific individual or character within the text

No Comments

No Known Activations