INDEX

Explanations

terms related to data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ãĥģãĥ¥

-0.16

zah

-0.15

aney

-0.15

ght

-0.14

êµ´

-0.14

ÑŁ

-0.14

çĶľ

-0.14

iem

-0.14

-lnd

-0.14

 knot

-0.14

POSITIVE LOGITS

borg

0.17

 carte

0.17

endregion

0.16

fest

0.16

íķŃ

0.15

mar

0.15

 Fraser

0.14

_bound

0.14

 Skull

0.14

lias

0.14

Activations Density 0.000%

terms related to data or statistics

No Comments

No Known Activations