INDEX

Explanations

occurrences of phrases expressing expectation or time-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 mastur

-0.16

à¥įà¤¦à¤°

-0.16

lernen

-0.15

ãĥ³ãĥĪ

-0.15

rente

-0.14

AGMA

-0.14

çľŁæŃ£

-0.14

fak

-0.14

ãĥ³ãĥĲ

-0.14

¾ç¤º

-0.14

POSITIVE LOGITS

 natural

0.73

natural

0.63

 Natural

0.60

Natural

0.54

 naturally

0.53

 logical

0.52

 natur

0.51

èĩªçĦ¶

0.47

 Logical

0.43

atural

0.42

Activations Density 0.260%

occurrences of phrases expressing expectation or time-related concepts

No Comments

No Known Activations