INDEX

Explanations

phrases that indicate conclusions or determinations made in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.SDK

-0.16

atis

-0.15

efe

-0.15

 Inst

-0.15

_UNIQUE

-0.14

Ing

-0.14

kes

-0.14

 Brennan

-0.14

iges

-0.14

fine

-0.14

POSITIVE LOGITS

nesc

0.18

/tags

0.17

azzi

0.16

Ownership

0.15

OTION

0.15

/goto

0.15

OKIE

0.15

 conclusion

0.14

ypass

0.14

 opposite

0.14

Activations Density 0.024%

phrases that indicate conclusions or determinations made in various contexts

No Comments

No Known Activations