INDEX

Explanations

occurrences of official meetings and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

asso

-0.17

lia

-0.15

ohl

-0.15

otime

-0.14

.Inject

-0.14

atchet

-0.13

 Ãĸr

-0.13

ichert

-0.13

aisal

-0.13

Ð°ÑģÑģ

-0.13

POSITIVE LOGITS

 held

1.15

held

0.98

 Held

0.96

-held

0.88

 hold

0.83

 holding

0.79

 holds

0.74

hold

0.69

 Hold

0.68

Hold

0.66

Activations Density 0.217%

occurrences of official meetings and events

No Comments

No Known Activations