INDEX

Explanations

sentiments and opinions regarding characters or concepts in various contexts

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

jem

-0.16

ÙĦÙĥØªØ±

-0.15

otomy

-0.15

lassen

-0.15

ilis

-0.14

ieri

-0.14

 thÃ´i

-0.14

andel

-0.13

oust

-0.13

 MySqlCommand

-0.13

POSITIVE LOGITS

 other

0.16

 incub

0.15

ollo

0.15

igo

0.15

 cand

0.14

ingly

0.14

inc

0.14

iband

0.14

 incur

0.14

anco

0.14

Activations Density 0.098%

sentiments and opinions regarding characters or concepts in various contexts

No Comments

No Known Activations