INDEX

Explanations

references to time, particularly related to past events or durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

lico

-0.16

PTY

-0.15

Pie

-0.15

Pik

-0.15

Pic

-0.15

ToFront

-0.15

Pocket

-0.15

 Painter

-0.14

Pic

-0.14

 Projection

-0.14

POSITIVE LOGITS

 past

1.02

past

0.88

 Past

0.82

Past

0.75

_past

0.69

 passed

0.58

 pasado

0.57

è¿ĩåİ»

0.56

 paste

0.49

pas

0.48

Activations Density 0.109%

references to time, particularly related to past events or durations

No Comments

No Known Activations