INDEX

Explanations

the term "biggest" and its variations, indicating a focus on comparisons or superlatives related to size or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Gins

-0.15

PasswordEncoder

-0.15

ORA

-0.14

usk

-0.14

 Tato

-0.14

bis

-0.14

onas

-0.14

uild

-0.13

æģµ

-0.13

quire

-0.13

POSITIVE LOGITS

ging

0.17

anging

0.16

iating

0.15

olph

0.14

ardi

0.14

caff

0.14

poke

0.14

iert

0.14

ouston

0.14

unta

0.14

Activations Density 0.018%

the term "biggest" and its variations, indicating a focus on comparisons or superlatives related to size or significance

No Comments

No Known Activations