INDEX

Explanations

references to characters and their developments in TV shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ettes

-0.16

ESIS

-0.16

atego

-0.15

Î±Î½Î¬

-0.15

itis

-0.15

 addCriterion

-0.14

afari

-0.14

 afect

-0.14

vetica

-0.13

 Buddha

-0.13

POSITIVE LOGITS

ancia

0.16

ATHER

0.14

 commenter

0.14

pen

0.14

Î¯Î¿ÏĤ

0.14

 omas

0.14

utow

0.14

ather

0.13

 novel

0.13

Activations Density 0.016%

references to characters and their developments in TV shows

No Comments

No Known Activations