INDEX

Explanations

phrases that indicate future intent or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

illas

-0.14

erty

-0.14

rape

-0.14

emas

-0.13

Yue

-0.13

 itself

-0.13

us

-0.13

doe

-0.13

ille

-0.13

usp

-0.13

POSITIVE LOGITS

oire

0.13

.chrome

0.13

 analog

0.13

 resembl

0.13

enstein

0.13

FormatException

0.13

adget

0.13

ĨĴ

0.13

_routing

0.13

Debe

0.13

Activations Density 0.055%

phrases that indicate future intent or actions

No Comments

No Known Activations