INDEX

Explanations

instances of the word "one," especially when it emphasizes singularity or distinction in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ivate

-0.16

acie

-0.15

 object

-0.15

acja

-0.15

_ht

-0.14

 Hercules

-0.14

prot

-0.14

stad

-0.14

si

-0.14

outh

-0.14

POSITIVE LOGITS

,readonly

0.16

.scalablytyped

0.15

ebek

0.15

ebra

0.15

åĭĴ

0.14

echan

0.14

ÌĨ

0.14

ç»©

0.14

porno

0.14

Activations Density 0.058%

instances of the word "one," especially when it emphasizes singularity or distinction in a context

No Comments

No Known Activations