INDEX

Explanations

instances of articles and demonstrative adjectives indicating specificity or quantity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

adoo

-0.17

hiba

-0.16

emma

-0.16

enda

-0.15

opoulos

-0.15

anel

-0.14

.criteria

-0.14

æĪ¶

-0.14

Äįka

-0.14

Ã¦k

-0.14

POSITIVE LOGITS

 æĶ

0.16

ãĥ³ãĥģ

0.15

lan

0.15

iding

0.14

_swap

0.14

Lor

0.14

-await

0.14

alker

0.13

anko

0.13

 scand

0.13

Activations Density 0.067%

instances of articles and demonstrative adjectives indicating specificity or quantity

No Comments

No Known Activations